{
    "_id": "D14-1162",
    "acl_id": "D14-1162",
    "paper_title": "Glove: Global Vectors for Word Representation",
    "ocr_title": "GloVe: Global Vectors for Word Representation",
    "publisher": "Association for Computational Linguistics",
    "sig_name": "SIGDAT",
    "venue_name": ["EMNLP"],
    "year": "2014",
    "month": "October",
    "address": "Doha, Qatar",
    "volume_name": "Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    "pages": "1532–1543",
    "doi": "10.3115/v1/D14-1162",
    "acl_author_id": [
        "jeffrey-pennington",
        "Richard Socher",
        "Christopher Manning"
    ],
    "acl_author_name": [
        "Jeffery Pennington",
        "richard-socher",
        "christopher-d-manning"
    ],
    "ocr_author": [
        {"email": "richard@socher.org", "name": "Richard Socher"},
        {"email": "manning@stanford.edu", "name": "Christopher D. Manning"},
        {"email": "jpennin@stanford.edu", "name": "Jeffrey Pennington"}
    ],
    "figure_caption": [
        "Figure 1: Weighting function f with = 3/4.",
        "Figure 2: Accuracy on the analogy task as function of vector size and window size/type. All models are trained on the 6 billion token corpus. In (a), the window size is 10. In (b) and (c), the vector size is 100."
    ],
    "table_caption": [
        "Table 1: Co-occurrence probabilities for target words ice and steam with selected context words from a 6 billion token corpus. Only in the ratio does noise from non-discriminative words like water and fashion cancel out, so that large values (much greater than 1) correlate well with properties specific to ice, and small values (much less than 1) correlate well with properties specific of steam.", 
        "Table 2: Results on the word analogy task, given as percent accuracy. Underlined scores are best within groups of similarly-sized models; bold scores are best overall. HPCA vectors are publicly available",
        ...
    ],
    "footnote": [
        "1 We could also include bias terms in Eqn. (16). ",
        "2 http://lebret.ch/words/ 3 http://code.google.com/p/word2vec/ 4 Levy et al. (2014) introduce a multiplicative analogy evaluation, 3COSMUL, and report an accuracy of 68.24% on ", 
        ...
    ],
    "url": [
        "http://lebret.ch/words/",
        "http://code.google.com/p/word2vec/"
    ],
    "domain": ["Lebret", "Google"],
    "ref_ACLcode": [
        "P12-1092",
        "E14-1051",
        ...
    ],
    "reference_cit2ref": [
        {
          "reference": "Tom M. Apostol. 1976. Introduction to Analytic Number Theory. Introduction to Analytic Num- ber Theory.",
          "cit2ref": "Apostol, 1976"
        },
        {
          "reference": "Marco Baroni, Georgiana Dinu, and Germ  an Kruszewski. 2014. Dont count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors. In ACL.",
          "cit2ref": "Baroni et al. (2014)"
        },
        {
          "reference": "Yoshua Bengio. 2009. Learning deep architectures for AI. Foundations and Trends in Machine Learning.",
          "cit2ref": "Bengio, 2009"
        },
        ...
    ]
    "task": [
        "namedentityrecognition",
        "semanticsimilarity",
        "informationretrieval",
        "questionanswering",
        "textcategorization"
    ],
    "approach": [
        "semi-supervisedlearning",
        "unsupervisedlearning"
    ],
    "linguistic": [
        "embeddings"
    ],
    "dataset_type": [
        "news"
    ],
    "languages": [
        "english"
    ],
    "total_citations": 1412,
    "citation_distribution": {
        "2014": 1,
        "2015": 108,
        "2016": 262,
        "2017": 340,
        "2018": 700,
        "2019": 1
    }
}

{
    "_id": "D14-1162",
    "year": "2014",
    "full_text": "Semantic vector space models of language represent ..."
}

{
    "_id": "christopher-d-manning",
    "all_coauthors": [
        "dan-jurafsky",
        "daniel-car",
        ...
    ],
    "all_papers_written": [
        "W08-0304",
        "W09-3206",
        ...
    ],
    "first_paper": 1993,
    "latest_paper": 2019,
    "total_papers": 204,
    "paper_distribution": {
        "1993": 1,
        "1998": 1,
        "1999": 1,
        ...
    },
    "dataset_types": {
        "news": 82,
        "blogs": 10,
        "twitter": 4,
        ...
    },
    "languages": {
        "chinese": 46,
        "arabic": 21,
        ...
    },
    "linguistic": {
        "discourse": 32,
        "embeddings": 35,
        ...
    },
    "tasks": {
        "discourseparsing": 1,
        "informationextraction": 39,
        ...
    },
    "approach": {
        "generativemodel": 14,
        "deeplearning": 17,
        ...
    },
    "total_citations": 9585,
    "citation_distribution": {
        "1994": 4,
        "1996": 2,
        ...
    }
}

{'_id': 'EMNLP-2017',
 'total_citations': 1403,
 'total_papers': 352,
 'venue_name': 'EMNLP',
 'year': '2017'
 'approach': {'bayesianmodel': 12,
    'dataanalysis': 5,
    'deeplearning': 79,
    'discriminativemodel': 12,
    'generativemodel': 26,
    'graphicalmodel': 23,
    'humancomputation': 1,
    'kernelmethod': 7,
    'multilingualresources': 1,
    'representationlearning': 29,
    'semi-supervisedlearning': 22,
    'structuredprediction': 20,
    'topicmodeling': 18,
    'unsupervisedlearning': 14},
 'dataset_type': {'biographies': 2,
    'biomedicaltexts': 3,
    'blogs': 26,
    'chat': 20,
    'childlanguage': 1,
    'encyclopedia': 7,
    'legaldocuments': 2,
    'literarytext': 3,
    'news': 136,
    'querylogs': 4,
    'scientificliterature': 1,
    'socialmedia': 53,
    'spokendialog': 11,
    'twitter': 44,
    'webcrawl': 2},
 'language': {'arabic': 13,
    'childlanguage': 1,
    'chinese': 76,
    'english': 204,
    'french': 44,
    'hebrew': 3,
    'hindi': 9,
    'japanese': 31,
    'korean': 7,
    'low-resourcelanguages': 5,
    'malay': 4,
    'multilingual': 52,
    'semitic': 4,
    'spanish': 40,
    'tamil': 2},
 'linguistic': {'codemixing': 1,
    'codeswitching': 2,
    'cognitivelinguistics': 2,
    'discourse': 74,
    'distributionalsemantics': 17,
    'embeddings': 208,
    'eventsemantics': 2,
    'formalsemantics': 3,
    'gesture': 1,
    'groundedsemantics': 1,
    'languagechange': 2,
    'lexicalsemantics': 9,
    'morphology': 19,
    'multilingualism': 1,
    'neurolinguistics': 1,
    'ontologies': 6,
    'phonetics': 4,
    'phonology': 7,
    'pragmatics': 4,
    'prosody': 3,
    'psycholinguistics': 3,
    'syntax': 66,
    'typology': 8},
 'task': {'argumentationmining': 7,
    'asr': 17,
    'biomedical': 13,
    'chunking': 16,
    'coreferenceresolution': 21,
    'corpusannotation': 2,
    'discourseparsing': 10,
    'ethics': 1,
    'eventdetection': 6,
    'imagedescriptiongeneration': 3,
    'informationextraction': 40,
    'informationretrieval': 40,
    'knowledgeacquisition': 3,
    'languagegeneration': 22,
    'languageidentification': 5,
    'languageunderstanding': 31,
    'machinetranslation': 137,
    'mathematicalmodels': 1,
    'morphologicalanalysis': 8,
    'namedentityrecognition': 30,
    'nativelanguageidentification': 1,
    'ocr': 27,
    'paraphrasing': 18,
    'questionanswering': 63,
    'relationextraction': 31,
    'semanticparsing': 35,
    'semanticsimilarity': 39,
    'sentimentanalysis': 54,
    'socialscience': 8,
    'spellingcorrection': 3,
    'spokenlanguageprocessing': 1,
    'styleanalysis': 2,
    'summarization': 52,
    'syntacticparsing': 13,
    'tagging': 91,
    'textcategorization': 4,
    'textorganization': 4,
    'textsimplification': 5,
    'textualentailment': 20,
    'videodescriptiongeneration': 1,
    'wordsegmentation': 18,
    'wordsensedisambiguation': 10},
 'reference_yearwise_conf': {'*SEMEVAL-2001': 2,
    '*SEMEVAL-2004': 7,
    '*SEMEVAL-2007': 7,
    '*SEMEVAL-2010': 6,
    '*SEMEVAL-2012': 6,
    '*SEMEVAL-2013': 17,
    '*SEMEVAL-2014': 11,
    '*SEMEVAL-2015': 15,
    '*SEMEVAL-2016': 20,
    '*SEMEVAL-2017': 5,
    'ACL-1986': 1,
    'ACL-1989': 4,
    'ACL-1996': 3,
    'ACL-1997': 1,
    .
    .
    .
    'WS-2012': 31,
    'WS-2013': 54,
    'WS-2014': 71,
    'WS-2015': 55,
    'WS-2016': 108,
    'WS-2017': 22},
 'citation_yearwise_conf': {'*SEMEVAL-2018': 42,
    'ACL-2017': 2,
    'ACL-2018': 314,
    'ALTA-2017': 1,
    'ALTA-2018': 4,
    'AMTA-2018': 5,
    'BEA-2018': 7,
    'CL-2018': 3,
    'CL-2019': 1,
    'CLPsych-2018': 5,
    'COLING-2018': 147,
    'CRAC-2018': 3,
    .
    .
    .
    'TRAC-2018': 1,
    'TextGraphs-2018': 2,
    'WASSA-2017': 1,
    'WAT-2017': 2,
    'WMT-2017': 4,
    'WMT-2018': 39,
    'WS-2017': 17,
    'WS-2018': 266,
    'WS-2019': 2},
}